The sticky buffer flow control for the ATM

Data from different applications — voice, video, file transfer, interactive — will be multiplexed in the future over broadband integrated services digital networks (BISDN). Data are segmented into 48-byte blocks prefixed by a 5-byte header and transported over the network using the asynchronous transfer mode (ATM).

An ATM connection-request is a contract between the user and the network; the user specifies a rate requirement, delay constraints, a bound on the cell-loss probability and other quality of service parameters. If the network can meet these requirements, a connection is made. Bursty traffic producing peak traffic rates in excess of the projected average rate could result in congestion and lead to performance degradation. As a result, the network might no longer be able to deliver the negotiated quality of service to existing connections. To lessen the chance of congestion, input rate control must be implemented.

This paper contains a performance analysis of the sticky buffer (SB), a moving window input rate control scheme intended to limit the rate at which input traffic may enter a network. Policing is achieved by buffering and hence delaying the entry of ATM-cells into the network. The scheme is determined by parameters (R,T) which specify that no more than R ATM-cells are permitted to enter the network in every window of size T cells. We present an exact analysis, deriving the probability generating function of the queue length distribution. A comparison with the leaky bucket is given. Our numerical examples show the required buffer size is comparable to that required by the leaky bucket.     

Discrete time analysis of leaky-bucket congestion control

Traffic control at an ATM multiplexer is of fundamental importance in B-ISDN. Due to the presence of large propagation delay, effective traffic control tends to use only local information. Leaky bucket has been introduced as a rate control method. The present paper studies the system performance of a leaky bucket controller with the arrivals being Poisson processes or Markov modulated Poisson processes (MMPP). Numerical results indicate that a small to medium sized controller is sufficient to attain the capability of a leaky bucket controller; increasing the size of the controller will not offer much improvement in performance. Controlling MMPP type of arrivals with a leaky bucket device may incur low performance especially when the burst duration is long. The performance can be improved by controlling a group of bursty users instead of a single bursty user.     

基于模糊控制的ATM网络VBR视频传输平滑策略

VBR视频传输的突发性是影响ATM网络服务质量的关键因素,文中通过模糊控制方法对视频传输流量的阈值进行监控,实现了接入的平滑并可动态调整传输速度。文中以传输流量及这发级作为评价指标进行分析,结果表明VBR视频传输自适应平滑策略的实效性。     

A neural network controller for congestion control in ATM multiplexers

This paper presents and adaptive approach to the problem of congestion control arising at the User-to Network Interface (UNI) of an ATM multiplexer. We view the ATM multiplexer as a non-linear stochastic system whose dynamics are ill-defined. Real-time measurements of the arrival rate process and the queueing process, are used to identify, and minimize congestion episodes. The performance of the system is evaluated using a performance-index function which is a quantative measure of “how well” the system is performing. A three-layers backpropagation neural network controller generates a signal that attempts to minimize congestion without degrading the quality of the traffic. During periods of buffer over-load the control signal, adaptively, modulates the arrival process such that its peak-rate is throttled-down. As soon as congestion is terminated, the control signal is adjusted such that the coding rates are restored back to their original values. Adaptability is achieved by continuously adjusting the weights of the neural network controller such that the performance of the system, measured by its performance index function, is maximized over a certain optimization period. The performance index function is defined in terms of two main objectives: (1) to minimize the cell loss rate (CLR), i.e., minimize congestion episodes, and (2) to maintain the quality of the video/audio traffic by maintaining its original source coding rate. The neural network learning process can be viewed as a specialized form of reinforcement learning in the sense that the control signal is reinforced if it tends to maximize the performance index function. Performance evaluation results prove that this approach is effective in controlling congestion while maintaining the quality of the traffic.     

ATM网络平台的仿真程序设计及初步流量分析

ATM网络是由一系列通过点对点ATM链路或接口相互连接的ATM交换机构成的网络。考虑到ATM网络中流量与拥塞控制的需要及QOS,特别需要有一个平台对其进行理论分析,文中设计了一个种基于微机上的ATM网络仿真平台,该ATM网络平台仿真主要是为分析ATM网络流量而设计的一个模拟整个ATM环境及各个设备行为的程序,可以较好地对ATM的流量与拥塞控制进行理论分析。     

基于网络演算的智能交通流量分配研究

精确的交通流量分配计算模型,能为实际的交通工程应用提供具体的流量出入速率或者信号灯控制时间方案,具有重大价值。首次将动态交通流量分配拟化为网络负载均衡问题,使用漏桶理论和网络演算方法,将交通的流量分配与路径时延转换为一系列极值运算,结合贪婪算法,以均衡网络延时为优化目标,得到交通配流。仿真结果表明,本模型在化解拥堵的同时,使分流后的道路平均延时普遍降低,能提升整体路网的通行能力。     

基于ABR业务模型的TCP协议性能分析

ＡＢＲ精力是ＡＴＭ中新定义的一种业务类型，经主要面向数据传输服务，采用基于速率的端到端的拥塞控制机制。ＴＣＰ是Ｉｎｔｅｒｎｔ所主要数据输协议。采用基于窗口的拥塞控制机制。文中主要讨论了讨论了ＴＣＰ与ＡＢＲ业务所采用的两种不同的拥塞控制机制，分析了基于ＡＢＲ的ＴＣＰ协议所呈的一些特点以及ＡＴＭ交换机缓存的大小对ＴＣＰ性能的影响。     

Packet video transport in ATM networks with single-bit feedback

The promise of a broadband integrated service digital network has led to the design of mechanisms for efficient transport of real-time compressed video in packet switching networks. We examine feedback control for video transport in ATM networks where the available feedback is a single bit of information carried in the cell header. We investigate the performance of three single-bit schemes for source rate adaptation. Two were originally for congestion control of bursty data traffic and are modified to control video traffic. The third scheme conveys more information about the state of queue(s) at the bottleneck. The simulation results show that all three schemes for feedback control of VBR video streams work remarkably well. During severe network congestion, the signal quality degrades gracefully, but not uniformly across all connections. Based on insights from the initial simulations, we propose a scheme to improve the fairness of service and demonstrate its effectiveness.     

混合散列连接算法随机I/O消除

混合散列连接算法(HHJ)是数据库管理系统查询处理中一种重要的连接算法. 本文提出通过缓存优化来减少随机I/O的缓存优化混合散列连接算法(OHHJ), 即通过合理优化分区阶段桶缓存的大小来尽量减少分区过程中产生的随机I/O. 文章通过对分区(桶)大小、桶缓存大小、可用缓存大小、关系表大小与硬盘随机I/O访问特性之间的关系进行定量分析, 得出桶大小以及桶缓存大小最优分配的启发式. 实验结果表明OHHJ可以较好地减少传统HHJ算法分区阶段产生的随机I/O, 提升了算法性能.     

Stable Queue Management in communication networks

Since Active Queue Management (AQM) was recommended by the Internet Engineering Task Force (IETF) as an efficient way to overcome performance limitations of Transmission Control Protocol (TCP), several studies have proven control theory to be a promising field for the design and analysis of congestion control in homogenous communication networks. AQM is gaining increased importance due to reports of buffer-induced latencies throughout the Internet. The increasing volume and diversity of traffic types (i.e., data, voice, and video) suggests that traffic management mechanisms, in general, and AQM schemes, specifically, must not only focus on the critical issue of congestion control but must also consider the QoS demands of heterogeneous traffic. However, to combine quality-of-service provisioning with congestion control, AQM design needs to be reconsidered. In this paper, we propose a state feedback controller design scheme for heterogeneous networks preserving the closed-loop system stability. Delay dependant stability conditions of the closed loop system are derived based on the Lyapunov-Krasovskii method. The proposed approach offers flexible choice of control parameters allowing the network administrator to control fairness and response time for each individual source node in a network of multiple links with different delay properties. The performance and robustness of the proposed controller were illustrated and analyzed using event-based computer simulations.     

Jitter in ATM networks and its impact on peak rate enforcement

Cells arriving to an ATM network experience random delays due to queueing in upstream multiplexing stages, notably in customer premises. This is the phenomenon of jitter and the aim of the present paper is to study its influence on peak rate enforcement. We first introduce some general characterizations of jitter and then, describe two models of jittered flows based on simple queueing systems. We discuss the objectives of peak rate enforcement and study the impact of jitter on the dimensioning of jumping window and leaky bucket mechanisms. A useful synthetic characterization of jitter appears to be a remote quantile of the cell delay distribution expressed in units of the initial inter-cell interval.     

A Multi-Agent Architecture for QoS Management in Multimedia Networks

Increasing interest in the transmission of audiovisual applications over best-effort networks (i.e., IP and ATM ABR, and UBR services) and efficient video-aware congestion control techniques have to be designed in order to improve the video quality in the presence of cell loss. This paper presents a new slice-based discard scheme to be used with Guaranteed Frame Rate service (formerly UBR+). The scheme adaptively and selectively adjusts discard levels to the switch's buffer occupancy, video cell payload types, and Forward Error Correction Drop Tolerance. To improve its performance, we introduce a distributed multiagent system that provides a self-regulating network control management by means of automatic adjustment of congestion control parameters. The control agents are distributed in the network and operate on a local scope referred to as a domain consisting of two adjacent ATM switches. The aim of the overall Intelligent Quality-of-Service (QoS) control framework is twofold. First, to ensure graceful picture quality degradation by minimizing the cell loss probability for critical video data while guaranteeing a bounded cell transfer delay. Second, to optimize the network effective throughput by reducing the transmission of nonuseful data. Performance evaluations show significant improvement over traditional approaches.     

ATM网络传输控制机制研究及进展

ATM网络中的传输控制方法的研究涉及到网络中的服务质量、服务类型。已经提出了许多不同特点的控制机制,主要集中在基于许可证方案和基于速率方案的设计,随着ATM广域网应用和因特网信息浏览的增多,新的研究热点是有速度反馈控制的用于ABR服务类型的传输控制技术。本文进一步研究和讨论ATM网络中所采用拥塞控制策略存在的问题和在当今网络应用考虑的主要因素。     

ATM网络模糊拥塞控制策略研究

ATM网络信息拥塞是制约网络发展的一个重要因素。本文针对单瓶颈节点网络,考虑两个饱和非线性因素,制定控制规则,寻找优化参数,设计模糊控制器。仿真结果表明在回路时延和可用带宽大幅波动的情况下,系统仍具有较好的控制效果,保证服务质量,进一步验证了算法的有效性。     

An Integrated Framework for Efficient Transport of Real-Time MPEG Video over ATM Best Effort Service

This paper describes a framework for the transport of real-time multimedia traffic generated by MPEG-2 applications over ATM networks using an enhanced UBR best effort service (UBR+). Based on the factors affecting the picture quality during transmission, we propose an efficient and cost-effective ATM best effort delivery service. The proposed framework integrates three major components: 1) a dynamic frame-level priority assignment mechanism based on MPEG data structure and feedback from the network (DexPAS), 2) a novel audio-visual AAL5 SSCS with FEC (AV-SSCS), and 3) an intelligent packet video discard scheme named FEC-PSD, which adaptively and selectively adjusts cell drop levels to switch buffer occupancy, video cell payload type and forward error correction capability of the destination. The overall best-effort video delivery framework is evaluated using ATM network simulation and MPEG2 video traces. The ultimate goal of this framework is twofold: First, minimizing loss of critical video data with bounded end-to-end delay for arriving cells and second, reducing the bad throughput crossing the network during congestion. Compared to previous approaches, performance evaluation shows a good protection of Predictive coded (P-) and Bi-directional Predictive coded (B-) frames at the MPEG video slice layer.     

A counter based congestion control (CBC) for ATM networks

This paper presents and analyzes a new congestion control strategy targeted toward integrated services in high speed ATM networks. The proposed control combines a new transmission control scheme with an existing access control to provide efficient, fair, and congestion-free network control. The transmission control scheme uses counters at each node to regulate the flow of packets from the output packet queues to the outgoing link. The transmission control is designed to be flexible in accomodating various existing and expected applications and to be simple in implementation. The resulting congestion control strategy supports different service rate for each service class according to its individual requirements and meets the GoS of each service class. The strategy is proven to provide bounded end-to-end queueing delay for each individual real-time application and at the same time give a best effort service to loss-sensitive and delay-tolerable data streams. An analytical model is presented to study the system state queueing behavior and the results how that the proposed strategy also has a good average performance.     

基于网络演算的簇树WSN性能上界分析

为保证WSN的服务质量(QoS),需精确求解其性能上界。对进入WSN节点的数据流进行漏桶管制,节点为数据流提供基于速率-延迟模型的服务保障,在已有簇状拓扑WSN性能模型研究基础上,利用确定性网络演算理论推导簇树WSN节点的有效带宽、缓冲区队列长度上界和数据流端到端延迟上界。     

基于ATM单瓶颈节点模型的PID拥塞控制器设计

针对ATM单瓶颈节点网络模型,提出ABR业务拥塞控制方案,给出使系统闭环稳定PID参数应满足的约束条件。设置前馈环节以抑制带宽波动对缓冲区队列长度的影响。仿真结果表明,业务服务质量得到了保证,系统具有较好的动态性能。     

Voice and video transmissions with global data parameter control for the IEEE 802.11e enhance distributed channel access

Best-effort data control and admission control are vital to guarantee quality of service for real-time (voice and video) transmissions in the IEEE 802.11e wireless LANs. In this paper, we propose and study a global data parameter control scheme integrated with a measurement-based admission control scheme for the IEEE 802.11e enhanced distributed channel access. In the proposed global data control scheme, the access point dynamically controls best-effort data parameters of stations globally based on traffic condition. Such a global/centralized data parameter control mechanism provides the best fairness for data transmissions among stations. In the proposed centrally-assisted distributed admission control scheme for voice and video transmissions, stations listen to available budgets from the access point to make decisions on acceptance or rejection of a voice or video stream. Such a scheme provides good differentiation among different access categories and provides good fairness among real-time streams within the same access category. The proposed mechanisms are evaluated via extensive simulations. Studies show that, with the proposed global data control scheme and the admission control scheme, quality of service can be greatly improved while maintaining a good utilization.     

Large scale enterprise ATM node with per-VC traffic control

On the backbone nodes of enterprise networks which handle data and voice traffic, complicated Quality of Service (QoS) capability, transmission efficiency, and high reliability are required. ATM technology satisfies those requirements. We have developed a large scale enterprise ATM node based on the shared buffer switch architecture. In the node, per-VC traffic control functions are implemented at low cost using centralized control of buffer write and read. In this paper, we explain the detail of the per-VC traffic control functions and show the performance results of ABR control using the node.